Markov decision processes with quasi-hyperbolic discounting
Sign Up to like & getrecommendations! Published in 2020 at "Finance and Stochastics"
DOI: 10.1007/s00780-020-00443-2
Abstract: We study Markov decision processes with Borel state spaces under quasi-hyperbolic discounting. This type of discounting nicely models human behaviour, which is time-inconsistent in the long run. The decision maker has preferences changing in time.… read more here.
Keywords: decision; markov decision; decision processes; hyperbolic discounting ... See more keywords
Continuous-Time Zero-Sum Games for Markov Decision Processes with Discounted Risk-Sensitive Cost Criterion
Sign Up to like & getrecommendations! Published in 2021 at "Dynamic Games and Applications"
DOI: 10.1007/s13235-021-00391-2
Abstract: In this paper, we study two-person zero-sum stochastic games for controlled continuous time Markov decision processes with risk-sensitive discounted cost criterion. The transition and cost rates are possibly unbounded. For the zero-sum stochastic game, we… read more here.
Keywords: markov decision; zero sum; continuous time; sum ... See more keywords
Semantic-based topic detection using Markov decision processes
Sign Up to like & getrecommendations! Published in 2017 at "Neurocomputing"
DOI: 10.1016/j.neucom.2017.02.020
Abstract: In the field of text mining, topic modeling and detection are fundamental problems in public opinion monitoring, information retrieval, social media analysis, and other activities. Document clustering has been used for topic detection at the… read more here.
Keywords: detection; using markov; markov decision; decision processes ... See more keywords
Risk-sensitive semi-Markov decision processes with general utilities and multiple criteria
Sign Up to like & getrecommendations! Published in 2018 at "Advances in Applied Probability"
DOI: 10.1017/apr.2018.36
Abstract: Abstract In this paper we investigate risk-sensitive semi-Markov decision processes with a Borel state space, unbounded cost rates, and general utility functions. The performance criteria are several expected utilities of the total cost in a… read more here.
Keywords: sensitive semi; risk sensitive; markov decision; decision processes ... See more keywords
Partially Observed Markov Decision Processes: From Filtering to Controlled Sensing [Bookshelf]
Sign Up to like & getrecommendations! Published in 2019 at "IEEE Control Systems"
DOI: 10.1109/mcs.2019.2913493
Abstract: Optimal decision making under uncertainty is of increasing importance in artificial intelligence, machine learning, signal processing, and control. Partially observed Markov decision processes (POMDPs) are a significant paradigm in real-world sequential decision making. The framework… read more here.
Keywords: markov decision; partially observed; observed markov; controlled sensing ... See more keywords
Policy Gradient for Continuing Tasks in Discounted Markov Decision Processes
Sign Up to like & getrecommendations! Published in 2022 at "IEEE Transactions on Automatic Control"
DOI: 10.1109/tac.2022.3163085
Abstract: Reinforcement learning aims to find policies that maximize an expected cumulative reward in Markov decision processes with unknown transition probabilities. Policy gradient (PG)-algorithms use stochastic gradients of the value function to update the policy. A… read more here.
Keywords: markov decision; decision processes; policy gradient; policy ... See more keywords
Intrinsically Motivated Hierarchical Policy Learning in Multiobjective Markov Decision Processes
Sign Up to like & getrecommendations! Published in 2021 at "IEEE Transactions on Cognitive and Developmental Systems"
DOI: 10.1109/tcds.2019.2948025
Abstract: The multiobjective Markov decision processes (MOMDPs) are sequential decision-making problems that involve multiple conflicting reward functions that cannot be optimized simultaneously without a compromise. This type of problem cannot be solved by a single optimal… read more here.
Keywords: markov decision; intrinsically motivated; multiobjective markov; policy ... See more keywords
An immediate-return reinforcement learning for the atypical Markov decision processes
Sign Up to like & getrecommendations! Published in 2022 at "Frontiers in Neurorobotics"
DOI: 10.3389/fnbot.2022.1012427
Abstract: The atypical Markov decision processes (MDPs) are decision-making for maximizing the immediate returns in only one state transition. Many complex dynamic problems can be regarded as the atypical MDPs, e.g., football trajectory control, approximations of… read more here.
Keywords: decision processes; reinforcement learning; markov decision; atypical mdps ... See more keywords